© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13822
    Prev
    Next
    INDEX
    Explanations

    since

    np_acts-logits-general · gemini-2.5-flash-lite

    so much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     если
    0.52
     якщо
    0.50
     hvis
    0.49
    Со
    0.48
    的确
    0.48
    Nếu
    0.47
    孟
    0.46
    если
    0.46
    Ό
    0.46
    Ре
    0.45
    POSITIVE LOGITS
    这么多
    0.60
     যেহেতু
    0.60
     இருப்பதால்
    0.59
    ないので
    0.54
     এতটা
    0.52
     sooo
    0.51
    হেতু
    0.50
    如此
    0.49
     unterschied
    0.47
     इतनी
    0.46
    Activations Density 0.219%

    No Known Activations